Greeting,
FYI, we noticed a 24.6% improvement of fio.read_iops due to commit:
commit: b9ff43dd27434dbd850b908e2e0e1f6e794efd9b ("mm/readahead: Fix readahead with large folios")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
in testcase: fio-basic
on test machine: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory
with following parameters:
disk: 2pmem
fs: xfs
runtime: 200s
nr_task: 50%
time_based: tb
rw: read
bs: 2M
ioengine: libaio
test_size: 200G
cpufreq_governor: performance
ucode: 0x500320a
test-description: Fio is a tool that will spawn a number of threads or processes doing a particular type of I/O action as specified by the user.
test-url: https://github.com/axboe/fio
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
sudo bin/lkp install job.yaml # job file is attached in this email
bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run
sudo bin/lkp run generated-yaml-file
# if come across any failure that blocks the test,
# please remove ~/.lkp and /lkp dir to run from a clean state.
=========================================================================================
bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/time_based/ucode:
2M/gcc-11/performance/2pmem/xfs/libaio/x86_64-rhel-8.3/50%/debian-10.4-x86_64-20200603.cgz/200s/read/lkp-csl-2sp7/200G/fio-basic/tb/0x500320a
commit:
170f37d6aa ("block: Do not call folio_next() on an unreferenced folio")
b9ff43dd27 ("mm/readahead: Fix readahead with large folios")
170f37d6aa6ad458 b9ff43dd27434dbd850b908e2e0
---------------- ---------------------------
%stddev %change %stddev
\ | \
0.58 ? 19% +2.0 2.60 ? 26% fio.latency_100ms%
0.05 ? 7% +0.0 0.06 ? 4% fio.latency_10ms%
0.08 ? 3% +0.0 0.10 fio.latency_20ms%
0.01 +0.0 0.02 ? 19% fio.latency_20us%
50.64 ? 6% +21.6 72.24 ? 4% fio.latency_250ms%
0.01 ? 15% +0.0 0.02 ? 9% fio.latency_4ms%
37.61 ? 10% -18.5 19.12 ? 10% fio.latency_500ms%
0.29 ? 13% +0.3 0.59 ? 23% fio.latency_50ms%
0.03 ? 2% -0.0 0.02 ? 14% fio.latency_50us%
10527 ? 3% +24.6% 13112 ? 2% fio.read_bw_MBps
5.019e+08 -34.1% 3.307e+08 ? 4% fio.read_clat_90%_us
5.578e+08 ? 3% +11.5% 6.222e+08 fio.read_clat_99%_us
2.797e+08 ? 3% -23.6% 2.136e+08 ? 3% fio.read_clat_mean_us
1.281e+08 ? 3% -8.6% 1.171e+08 ? 4% fio.read_clat_stddev
5263 ? 3% +24.6% 6556 ? 2% fio.read_iops
9048337 ? 3% -23.6% 6917228 ? 3% fio.read_slat_mean_us
4.313e+09 ? 3% +24.6% 5.374e+09 ? 2% fio.time.file_system_inputs
23336 +19.0% 27773 fio.time.involuntary_context_switches
20117 +2.4% 20595 fio.time.voluntary_context_switches
1052766 ? 3% +24.6% 1311719 ? 2% fio.workload
444.29 +2.6% 455.70 pmeter.Average_Active_Power
745.95 ? 15% -25.4% 556.35 ? 26% sched_debug.cpu.clock_task.stddev
0.34 ? 4% -0.1 0.28 ? 9% mpstat.cpu.all.soft%
0.46 ? 4% -0.1 0.40 ? 4% mpstat.cpu.all.usr%
10622900 ? 3% +24.2% 13191820 ? 2% vmstat.io.bi
1834 +5.4% 1934 ? 2% vmstat.system.cs
0.02 +50.0% 0.03 turbostat.IPC
270.10 +2.2% 276.04 turbostat.PkgWatt
55.53 +5.2% 58.42 turbostat.RAMWatt
109247 +79.2% 195797 meminfo.KReclaimable
109247 +79.2% 195797 meminfo.SReclaimable
217681 +19.1% 259279 meminfo.SUnreclaim
326930 +39.2% 455077 meminfo.Slab
5737532 ? 8% -37.1% 3607917 ? 12% numa-meminfo.node0.MemFree
199707 ? 9% +18.8% 237210 ? 8% numa-meminfo.node0.Slab
70882880 -7.9% 65286368 numa-meminfo.node1.FilePages
34447 ? 46% +181.2% 96863 ? 21% numa-meminfo.node1.KReclaimable
34447 ? 46% +181.2% 96863 ? 21% numa-meminfo.node1.SReclaimable
92783 ? 13% +30.4% 120973 ? 4% numa-meminfo.node1.SUnreclaim
127231 ? 16% +71.2% 217837 ? 10% numa-meminfo.node1.Slab
1999077 ? 10% +2766.7% 57307801 ? 9% numa-numastat.node0.local_node
1563227 ? 6% +1028.4% 17638837 ? 13% numa-numastat.node0.numa_foreign
2029367 ? 8% +2725.7% 57343211 ? 9% numa-numastat.node0.numa_hit
2483793 +1789.7% 46937375 ? 3% numa-numastat.node1.local_node
2540984 ? 2% +1748.9% 46979938 ? 3% numa-numastat.node1.numa_hit
1563227 ? 6% +1028.5% 17641255 ? 13% numa-numastat.node1.numa_miss
1620419 ? 5% +991.7% 17690341 ? 13% numa-numastat.node1.other_node
1443532 ? 9% -36.5% 916868 ? 11% numa-vmstat.node0.nr_free_pages
1563227 ? 6% +1028.1% 17634435 ? 13% numa-vmstat.node0.numa_foreign
2028586 ? 8% +2726.7% 57342654 ? 9% numa-vmstat.node0.numa_hit
1998296 ? 10% +2767.8% 57307244 ? 9% numa-vmstat.node0.numa_local
36.67 ? 53% +1811.4% 700.83 ? 77% numa-vmstat.node0.workingset_nodes
17728775 -8.0% 16313974 numa-vmstat.node1.nr_file_pages
8608 ? 46% +181.3% 24217 ? 21% numa-vmstat.node1.nr_slab_reclaimable
23193 ? 13% +30.4% 30249 ? 4% numa-vmstat.node1.nr_slab_unreclaimable
2539777 ? 2% +1749.7% 46977008 ? 3% numa-vmstat.node1.numa_hit
2482586 +1790.5% 46934445 ? 3% numa-vmstat.node1.numa_local
1563227 ? 6% +1028.3% 17638159 ? 13% numa-vmstat.node1.numa_miss
1620419 ? 5% +991.5% 17687245 ? 13% numa-vmstat.node1.numa_other
13.33 ? 75% +825.0% 123.33 ? 49% numa-vmstat.node1.workingset_nodes
1763507 ? 55% +780.7% 15530641 ? 22% proc-vmstat.compact_free_scanned
119086 ? 23% +2522.4% 3122933 ? 22% proc-vmstat.compact_isolated
15615625 ? 21% +187.5% 44901482 ? 20% proc-vmstat.compact_migrate_scanned
27095029 -3.3% 26209667 proc-vmstat.nr_file_pages
49156688 +1.8% 50045472 proc-vmstat.nr_free_pages
26487821 -3.3% 25602197 proc-vmstat.nr_inactive_file
27308 +79.2% 48936 proc-vmstat.nr_slab_reclaimable
54414 +19.1% 64800 proc-vmstat.nr_slab_unreclaimable
26487796 -3.3% 25602050 proc-vmstat.nr_zone_inactive_file
1563227 ? 6% +1028.4% 17638837 ? 13% proc-vmstat.numa_foreign
4571892 ? 5% +2181.9% 1.043e+08 ? 5% proc-vmstat.numa_hit
4484412 ? 5% +2224.7% 1.042e+08 ? 5% proc-vmstat.numa_local
1563227 ? 6% +1028.5% 17641255 ? 13% proc-vmstat.numa_miss
1650404 ? 6% +974.2% 17728591 ? 13% proc-vmstat.numa_other
4869791 ? 7% +193.1% 14274576 ? 15% proc-vmstat.pgalloc_dma32
5.349e+08 ? 3% +44.0% 7.701e+08 ? 2% proc-vmstat.pgalloc_normal
5.148e+08 ? 3% +48.5% 7.648e+08 ? 2% proc-vmstat.pgfree
438716 ? 3% +348.4% 1967046 ? 18% proc-vmstat.pgmigrate_success
2.156e+09 ? 3% +24.6% 2.687e+09 ? 2% proc-vmstat.pgpgin
0.83 ? 82% +93540.0% 780.33 ? 49% proc-vmstat.pgrotated
4204993 ? 60% +348.7% 18868882 ? 48% proc-vmstat.pgscan_file
4203671 ? 60% +348.8% 18865293 ? 48% proc-vmstat.pgscan_kswapd
4204381 ? 60% +343.2% 18635881 ? 48% proc-vmstat.pgsteal_file
4203058 ? 60% +343.3% 18632292 ? 48% proc-vmstat.pgsteal_kswapd
49.17 ? 54% +1609.8% 840.67 ? 76% proc-vmstat.workingset_nodes
60.67 -16.5% 50.68 perf-stat.i.MPKI
1.803e+09 ? 3% +64.5% 2.966e+09 ? 2% perf-stat.i.branch-instructions
6184540 ? 2% +65.7% 10250205 ? 4% perf-stat.i.branch-misses
92.07 -5.4 86.67 perf-stat.i.cache-miss-rate%
5.857e+08 ? 3% +22.3% 7.161e+08 ? 2% perf-stat.i.cache-misses
6.342e+08 ? 3% +30.4% 8.268e+08 ? 3% perf-stat.i.cache-references
1701 +6.1% 1805 ? 2% perf-stat.i.context-switches
14.93 ? 3% -37.1% 9.38 ? 3% perf-stat.i.cpi
294.07 ? 2% -18.7% 239.15 ? 4% perf-stat.i.cycles-between-cache-misses
0.01 ? 6% +0.0 0.01 ? 6% perf-stat.i.dTLB-load-miss-rate%
94987 ? 5% +259.1% 341113 ? 8% perf-stat.i.dTLB-load-misses
1.937e+09 ? 3% +68.9% 3.27e+09 ? 2% perf-stat.i.dTLB-loads
0.00 ? 2% +0.0 0.01 ? 3% perf-stat.i.dTLB-store-miss-rate%
70696 ? 3% +268.4% 260434 ? 5% perf-stat.i.dTLB-store-misses
1.673e+09 ? 3% +51.9% 2.542e+09 ? 2% perf-stat.i.dTLB-stores
40.11 ? 6% +6.7 46.85 ? 5% perf-stat.i.iTLB-load-miss-rate%
979065 ? 4% +60.4% 1570764 ? 7% perf-stat.i.iTLB-load-misses
1.035e+10 ? 3% +57.2% 1.627e+10 ? 2% perf-stat.i.instructions
0.08 ? 2% +57.1% 0.12 ? 2% perf-stat.i.ipc
15.20 -2.9% 14.75 perf-stat.i.major-faults
1584 ? 3% -25.4% 1182 ? 8% perf-stat.i.metric.K/sec
64.32 ? 3% +59.1% 102.30 ? 2% perf-stat.i.metric.M/sec
39.71 ? 5% -10.0 29.70 ? 5% perf-stat.i.node-load-miss-rate%
39204201 ? 3% -7.6% 36215971 ? 2% perf-stat.i.node-load-misses
83792143 ? 5% +29.0% 1.081e+08 ? 3% perf-stat.i.node-loads
38.00 ? 5% -12.9 25.08 ? 7% perf-stat.i.node-store-miss-rate%
49443672 ? 2% -19.6% 39741233 ? 5% perf-stat.i.node-store-misses
1.042e+08 ? 4% +40.2% 1.461e+08 ? 4% perf-stat.i.node-stores
61.24 -17.1% 50.79 perf-stat.overall.MPKI
92.36 -5.7 86.66 perf-stat.overall.cache-miss-rate%
13.47 ? 3% -36.9% 8.50 ? 2% perf-stat.overall.cpi
238.08 ? 3% -18.9% 193.04 ? 2% perf-stat.overall.cycles-between-cache-misses
0.00 ? 6% +0.0 0.01 ? 7% perf-stat.overall.dTLB-load-miss-rate%
0.00 ? 2% +0.0 0.01 ? 4% perf-stat.overall.dTLB-store-miss-rate%
40.38 ? 6% +8.1 48.52 ? 5% perf-stat.overall.iTLB-load-miss-rate%
0.07 ? 2% +58.5% 0.12 ? 2% perf-stat.overall.ipc
32.50 ? 5% -7.1 25.37 ? 4% perf-stat.overall.node-load-miss-rate%
32.71 ? 4% -11.1 21.63 ? 7% perf-stat.overall.node-store-miss-rate%
1954187 +26.8% 2478091 perf-stat.overall.path-length
1.778e+09 ? 3% +65.0% 2.934e+09 ? 2% perf-stat.ps.branch-instructions
6104343 ? 2% +65.9% 10124383 ? 4% perf-stat.ps.branch-misses
5.775e+08 ? 3% +22.8% 7.09e+08 ? 2% perf-stat.ps.cache-misses
6.252e+08 ? 3% +30.8% 8.181e+08 ? 3% perf-stat.ps.cache-references
1685 +6.1% 1788 ? 2% perf-stat.ps.context-switches
130.84 +1.3% 132.52 perf-stat.ps.cpu-migrations
93751 ? 5% +259.7% 337214 ? 8% perf-stat.ps.dTLB-load-misses
1.911e+09 ? 3% +69.3% 3.236e+09 ? 2% perf-stat.ps.dTLB-loads
69811 ? 3% +268.8% 257492 ? 5% perf-stat.ps.dTLB-store-misses
1.651e+09 ? 3% +52.4% 2.515e+09 ? 2% perf-stat.ps.dTLB-stores
971749 ? 4% +59.6% 1550920 ? 7% perf-stat.ps.iTLB-load-misses
1.021e+10 ? 3% +57.7% 1.61e+10 ? 2% perf-stat.ps.instructions
39356027 ? 3% -8.0% 36218463 ? 2% perf-stat.ps.node-load-misses
81906530 ? 5% +30.3% 1.067e+08 ? 4% perf-stat.ps.node-loads
49511032 ? 3% -19.7% 39746307 ? 5% perf-stat.ps.node-store-misses
1.02e+08 ? 5% +41.5% 1.443e+08 ? 4% perf-stat.ps.node-stores
2.057e+12 ? 3% +58.0% 3.25e+12 ? 2% perf-stat.total.instructions
0.00 +0.7 0.67 ? 7% perf-profile.calltrace.cycles-pp.folio_mark_accessed.filemap_read.xfs_file_buffered_read.xfs_file_read_iter.aio_read
0.00 +0.7 0.71 ? 8% perf-profile.calltrace.cycles-pp.rmqueue.get_page_from_freelist.__alloc_pages.folio_alloc.page_cache_ra_order
0.00 +0.8 0.80 ? 9% perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages.folio_alloc.page_cache_ra_order.filemap_get_pages
0.00 +0.8 0.84 ? 8% perf-profile.calltrace.cycles-pp.__alloc_pages.folio_alloc.page_cache_ra_order.filemap_get_pages.filemap_read
0.00 +0.9 0.87 ? 8% perf-profile.calltrace.cycles-pp.folio_alloc.page_cache_ra_order.filemap_get_pages.filemap_read.xfs_file_buffered_read
0.00 +1.1 1.12 ? 29% perf-profile.calltrace.cycles-pp.__filemap_add_folio.filemap_add_folio.page_cache_ra_order.filemap_get_pages.filemap_read
0.00 +1.7 1.68 ? 30% perf-profile.calltrace.cycles-pp.filemap_add_folio.page_cache_ra_order.filemap_get_pages.filemap_read.xfs_file_buffered_read
0.00 +1.8 1.77 ? 64% perf-profile.calltrace.cycles-pp.uncharge_batch.__mem_cgroup_uncharge.free_compound_page.release_pages.__pagevec_release
0.00 +1.8 1.78 ? 63% perf-profile.calltrace.cycles-pp.__mem_cgroup_uncharge.free_compound_page.release_pages.__pagevec_release.invalidate_mapping_pagevec
0.00 +1.8 1.78 ? 63% perf-profile.calltrace.cycles-pp.free_compound_page.release_pages.__pagevec_release.invalidate_mapping_pagevec.generic_fadvise
0.78 ? 10% +1.9 2.65 ? 19% perf-profile.calltrace.cycles-pp.page_cache_ra_order.filemap_get_pages.filemap_read.xfs_file_buffered_read.xfs_file_read_iter
0.00 +3.8 3.78 ? 9% perf-profile.calltrace.cycles-pp.__submit_bio.__submit_bio_noacct.iomap_readahead.read_pages.page_cache_ra_unbounded
0.00 +3.8 3.78 ? 9% perf-profile.calltrace.cycles-pp.__submit_bio_noacct.iomap_readahead.read_pages.page_cache_ra_unbounded.filemap_get_pages
0.00 +3.9 3.87 ? 9% perf-profile.calltrace.cycles-pp.iomap_readahead.read_pages.page_cache_ra_unbounded.filemap_get_pages.filemap_read
0.00 +3.9 3.88 ? 9% perf-profile.calltrace.cycles-pp.read_pages.page_cache_ra_unbounded.filemap_get_pages.filemap_read.xfs_file_buffered_read
0.00 +4.1 4.06 ? 41% perf-profile.calltrace.cycles-pp.release_pages.__pagevec_release.invalidate_mapping_pagevec.generic_fadvise.ksys_fadvise64_64
0.00 +4.1 4.07 ? 41% perf-profile.calltrace.cycles-pp.__pagevec_release.invalidate_mapping_pagevec.generic_fadvise.ksys_fadvise64_64.__x64_sys_fadvise64
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.invalidate_mapping_pagevec.generic_fadvise.ksys_fadvise64_64.__x64_sys_fadvise64.do_syscall_64
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.posix_fadvise
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.posix_fadvise
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.posix_fadvise
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.__x64_sys_fadvise64.do_syscall_64.entry_SYSCALL_64_after_hwframe.posix_fadvise
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.ksys_fadvise64_64.__x64_sys_fadvise64.do_syscall_64.entry_SYSCALL_64_after_hwframe.posix_fadvise
0.09 ?223% +4.7 4.80 ? 37% perf-profile.calltrace.cycles-pp.generic_fadvise.ksys_fadvise64_64.__x64_sys_fadvise64.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +4.7 4.74 ? 8% perf-profile.calltrace.cycles-pp.page_cache_ra_unbounded.filemap_get_pages.filemap_read.xfs_file_buffered_read.xfs_file_read_iter
0.07 ? 15% +0.0 0.11 ? 12% perf-profile.children.cycles-pp.kmem_cache_free
0.03 ?100% +0.1 0.08 ? 11% perf-profile.children.cycles-pp.iomap_page_create
0.02 ?141% +0.1 0.07 ? 10% perf-profile.children.cycles-pp.iomap_iop_set_range_uptodate
0.00 +0.1 0.06 ? 7% perf-profile.children.cycles-pp.smpboot_thread_fn
0.00 +0.1 0.06 ? 14% perf-profile.children.cycles-pp.rcu_do_batch
0.14 ? 14% +0.1 0.21 ? 10% perf-profile.children.cycles-pp.iomap_readpage_iter
0.00 +0.1 0.07 ? 17% perf-profile.children.cycles-pp.rcu_core
0.06 ? 16% +0.1 0.13 ? 11% perf-profile.children.cycles-pp.__mod_node_page_state
0.00 +0.1 0.08 ? 12% perf-profile.children.cycles-pp.get_mem_cgroup_from_mm
0.06 ? 17% +0.1 0.14 ? 9% perf-profile.children.cycles-pp.__mod_lruvec_state
0.00 +0.1 0.09 ? 6% perf-profile.children.cycles-pp.kmem_cache_alloc_lru
0.00 +0.1 0.09 ? 6% perf-profile.children.cycles-pp.xas_alloc
0.00 +0.1 0.10 ? 33% perf-profile.children.cycles-pp.memcg_check_events
0.00 +0.1 0.11 ? 13% perf-profile.children.cycles-pp.xa_load
0.00 +0.1 0.12 ? 5% perf-profile.children.cycles-pp.xas_create
0.00 +0.1 0.12 ? 18% perf-profile.children.cycles-pp.__mod_memcg_lruvec_state
0.07 ? 15% +0.1 0.20 ? 11% perf-profile.children.cycles-pp.xas_load
0.10 ? 10% +0.2 0.25 ? 9% perf-profile.children.cycles-pp.filemap_get_read_batch
0.13 ? 59% +0.2 0.29 ? 19% perf-profile.children.cycles-pp.filemap_unaccount_folio
0.03 ? 70% +0.2 0.19 ? 15% perf-profile.children.cycles-pp.__pagevec_lru_add_fn
0.08 ? 8% +0.2 0.24 ? 9% perf-profile.children.cycles-pp.iomap_read_end_io
0.03 ?105% +0.2 0.23 ? 21% perf-profile.children.cycles-pp.__free_pages_ok
0.06 ? 49% +0.2 0.27 ? 12% perf-profile.children.cycles-pp.__list_del_entry_valid
0.06 ? 17% +0.2 0.28 ? 22% perf-profile.children.cycles-pp.__mod_lruvec_page_state
0.01 ?223% +0.2 0.23 ? 6% perf-profile.children.cycles-pp.xas_store
0.14 ? 58% +0.2 0.38 ? 17% perf-profile.children.cycles-pp.__filemap_remove_folio
0.00 +0.2 0.24 ? 23% perf-profile.children.cycles-pp.__free_one_page
0.00 +0.3 0.26 ? 17% perf-profile.children.cycles-pp.find_lock_entries
0.14 ? 58% +0.3 0.40 ? 18% perf-profile.children.cycles-pp.remove_mapping
0.14 ? 58% +0.3 0.42 ? 18% perf-profile.children.cycles-pp.__remove_mapping
0.00 +0.3 0.28 ? 54% perf-profile.children.cycles-pp.free_transhuge_page
0.12 ? 52% +0.3 0.45 ? 39% perf-profile.children.cycles-pp.ret_from_fork
0.12 ? 54% +0.3 0.45 ? 39% perf-profile.children.cycles-pp.kthread
0.00 +0.3 0.33 ? 59% perf-profile.children.cycles-pp.__mem_cgroup_uncharge_list
0.00 +0.3 0.34 ? 10% perf-profile.children.cycles-pp.rmqueue_bulk
0.01 ?223% +0.5 0.50 ? 44% perf-profile.children.cycles-pp.__page_cache_release
0.07 ? 23% +0.5 0.59 ? 44% perf-profile.children.cycles-pp.page_counter_try_charge
0.09 ? 19% +0.6 0.69 ? 56% perf-profile.children.cycles-pp.__pagevec_lru_add
0.36 ? 8% +0.6 0.96 ? 8% perf-profile.children.cycles-pp.rmqueue
0.08 ? 17% +0.6 0.70 ? 55% perf-profile.children.cycles-pp.folio_add_lru
0.00 +0.7 0.66 ? 30% perf-profile.children.cycles-pp._raw_spin_lock
0.00 +0.7 0.66 ? 65% perf-profile.children.cycles-pp.propagate_protected_usage
0.40 ? 8% +0.7 1.08 ? 8% perf-profile.children.cycles-pp.get_page_from_freelist
0.00 +0.7 0.68 ? 7% perf-profile.children.cycles-pp.folio_mark_accessed
0.08 ? 26% +0.7 0.77 ? 44% perf-profile.children.cycles-pp.try_charge_memcg
0.44 ? 8% +0.7 1.15 ? 8% perf-profile.children.cycles-pp.__alloc_pages
0.11 ? 20% +0.7 0.84 ? 42% perf-profile.children.cycles-pp.charge_memcg
0.43 ? 8% +0.7 1.16 ? 8% perf-profile.children.cycles-pp.folio_alloc
0.00 +0.8 0.75 ? 30% perf-profile.children.cycles-pp.free_pcppages_bulk
0.15 ? 16% +0.8 0.92 ? 39% perf-profile.children.cycles-pp.__mem_cgroup_charge
0.00 +0.8 0.78 ? 30% perf-profile.children.cycles-pp.free_unref_page
0.02 ?142% +0.9 0.91 ? 61% perf-profile.children.cycles-pp.folio_lruvec_lock_irqsave
0.26 ? 14% +1.2 1.46 ? 28% perf-profile.children.cycles-pp.__filemap_add_folio
0.11 ? 26% +1.5 1.60 ? 39% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.02 ?142% +1.7 1.72 ? 33% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
0.00 +1.8 1.81 ? 63% perf-profile.children.cycles-pp.free_compound_page
0.34 ? 13% +1.8 2.16 ? 28% perf-profile.children.cycles-pp.filemap_add_folio
0.78 ? 10% +1.9 2.65 ? 19% perf-profile.children.cycles-pp.page_cache_ra_order
0.00 +1.9 1.93 ? 61% perf-profile.children.cycles-pp.__mem_cgroup_uncharge
0.00 +2.1 2.11 ? 62% perf-profile.children.cycles-pp.page_counter_uncharge
0.00 +2.2 2.22 ? 61% perf-profile.children.cycles-pp.uncharge_batch
0.11 ? 58% +4.0 4.07 ? 41% perf-profile.children.cycles-pp.__pagevec_release
0.12 ? 55% +4.0 4.14 ? 41% perf-profile.children.cycles-pp.release_pages
0.27 ? 58% +4.5 4.80 ? 37% perf-profile.children.cycles-pp.posix_fadvise
0.27 ? 58% +4.5 4.80 ? 37% perf-profile.children.cycles-pp.__x64_sys_fadvise64
0.27 ? 58% +4.5 4.80 ? 37% perf-profile.children.cycles-pp.ksys_fadvise64_64
0.27 ? 58% +4.5 4.80 ? 37% perf-profile.children.cycles-pp.generic_fadvise
0.27 ? 58% +4.5 4.80 ? 37% perf-profile.children.cycles-pp.invalidate_mapping_pagevec
0.00 +4.7 4.74 ? 8% perf-profile.children.cycles-pp.page_cache_ra_unbounded
0.07 ? 8% +0.0 0.09 ? 6% perf-profile.self.cycles-pp.copy_page_to_iter
0.00 +0.1 0.05 ? 7% perf-profile.self.cycles-pp.xas_store
0.10 ? 10% +0.1 0.16 ? 10% perf-profile.self.cycles-pp.filemap_read
0.00 +0.1 0.06 ? 14% perf-profile.self.cycles-pp._raw_spin_lock
0.00 +0.1 0.06 ? 11% perf-profile.self.cycles-pp.iomap_readahead
0.00 +0.1 0.06 ? 7% perf-profile.self.cycles-pp.rmqueue
0.00 +0.1 0.07 ? 29% perf-profile.self.cycles-pp.__pagevec_lru_add_fn
0.06 ? 16% +0.1 0.13 ? 11% perf-profile.self.cycles-pp.__mod_node_page_state
0.00 +0.1 0.07 ? 12% perf-profile.self.cycles-pp.get_mem_cgroup_from_mm
0.00 +0.1 0.08 ? 8% perf-profile.self.cycles-pp.get_page_from_freelist
0.00 +0.1 0.09 ? 17% perf-profile.self.cycles-pp.rmqueue_bulk
0.00 +0.1 0.12 ? 21% perf-profile.self.cycles-pp.__mod_memcg_lruvec_state
0.00 +0.1 0.14 ? 11% perf-profile.self.cycles-pp.iomap_read_end_io
0.03 ?100% +0.1 0.17 ? 11% perf-profile.self.cycles-pp.xas_load
0.00 +0.1 0.14 ? 30% perf-profile.self.cycles-pp.__mod_lruvec_page_state
0.00 +0.2 0.15 ? 21% perf-profile.self.cycles-pp.release_pages
0.00 +0.2 0.17 ? 11% perf-profile.self.cycles-pp.filemap_get_read_batch
0.00 +0.2 0.18 ? 46% perf-profile.self.cycles-pp.try_charge_memcg
0.00 +0.2 0.19 ? 25% perf-profile.self.cycles-pp.__free_one_page
0.06 ? 49% +0.2 0.27 ? 12% perf-profile.self.cycles-pp.__list_del_entry_valid
0.00 +0.2 0.23 ? 17% perf-profile.self.cycles-pp.find_lock_entries
0.06 ? 51% +0.4 0.46 ? 41% perf-profile.self.cycles-pp.page_counter_try_charge
0.08 ? 16% +0.4 0.49 ? 33% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.00 +0.7 0.66 ? 65% perf-profile.self.cycles-pp.propagate_protected_usage
0.00 +0.7 0.67 ? 7% perf-profile.self.cycles-pp.folio_mark_accessed
0.00 +1.6 1.58 ? 60% perf-profile.self.cycles-pp.page_counter_uncharge
0.02 ?142% +1.7 1.71 ? 33% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
--
0-DAY CI Kernel Test Service
https://01.org/lkp